Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
Pattern recognition in imaging data by >300,000 players of a global, online, commercial computer game is combined with deep learning to improve the accuracy of annotation of subcellular protein localization.
Combining four years of field data with computer modeling reveals that development of resistance to Bacillus thuringiensis insecticidal proteins (Bt) in cotton bollworm can be delayed by refuges of non-Bt host plants other than cotton, but that these so-called ‘natural refuges’ are not as effective as non-Bt cotton refuges.
An open competition to predict the progression of amyotrophic lateral sclerosis (ALS, also known as Lou Gehrig's disease) disease from the largest database of ALS clinical trial data yields potential new biomarkers and algorithms that outperform human clinicians.
An elegant mathematical model supported by experiments in Escherichia coli demonstrates how clustering enzymes can efficiently channel intermediates from one enzyme to the next, facilitating rational engineering of metabolism.
For several cancer types analyzed by The Cancer Genome Atlas project, predictions of patient survival were not substantially improved by using common data mining approaches to combine traditional clinical variables with molecular profiling data.